Eye Movement Analysis for Activity Recognition Using Electrooculography

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 33; no. 4; pp. 741 - 753
• Main Authors: Bulling, Andreas, Ward, Jamie A, Gellersen, Hans, Tröster, Gerhard
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.04.2011; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acoustic sensors; Adult; Algorithms; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Data processing. List processing. Character string processing; Detection; Ear; Electrooculography; Electrooculography - methods; Exact sciences and technology; Eye movements; Eye Movements - physiology; Eyes; feature evaluation and selection; Female; Humans; Male; Memory organisation. Data processing; Middle Aged; pattern analysis; Pattern recognition; Pattern recognition. Digital image processing. Computational geometry; Recognition; Reproduction; signal processing; Signal processing algorithms; Software; Support vector machine classification; Support vector machines; Ubiquitous computing; Visual Perception - physiology; Wearable computers; Pervasive computing; Electrooculography; feature evaluation and selection; Redundancy; Ubiquitous computing; Eye movement; Specific activity; Relevance; Dimension reduction; Human activity; Scene analysis; Database; Vector support machine; Signal processing; Pattern analysis; Mobile computing
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2010.86

In this work, we investigate eye movement analysis as a new sensing modality for activity recognition. Eye movement data were recorded using an electrooculography (EOG) system. We first describe and evaluate algorithms for detecting three eye movement characteristics from EOG signals-saccades, fixations, and blinks-and propose a method for assessing repetitive patterns of eye movements. We then devise 90 different features based on these characteristics and select a subset of them using minimum redundancy maximum relevance (mRMR) feature selection. We validate the method using an eight participant study in an office environment using an example set of five activity classes: copying a text, reading a printed paper, taking handwritten notes, watching a video, and browsing the Web. We also include periods with no specific activity (the NULL class). Using a support vector machine (SVM) classifier and person-independent (leave-one-person-out) training, we obtain an average precision of 76.1 percent and recall of 70.5 percent over all classes and participants. The work demonstrates the promise of eye-based activity recognition (EAR) and opens up discussion on the wider applicability of EAR to other activities that are difficult, or even impossible, to detect using common sensing modalities.